Memory system for voice agents that stores facts and emotion/persona in a graph and retrieves only relevant memories.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
VoiceMem is a memory system for voice agents. Its project page describes a graph-based memory split into two parts: an "Informative Left Brain" for factual information and an "Emotion & Persona Right Brain" for preferences and emotional or persona-related content.
According to a YouTube creator summary, it retrieves only the memories relevant to the current turn from the graph. This reportedly gave better memory accuracy, fewer tokens and sub-second latency compared with competing methods. These claims come from the video and were not verified against the project pages, which contain little detail. Code is reported to have been released, but no repository link was available in the provided material.
It is aimed at developers building conversational voice agents that need long-term memory across sessions. Vendor, license, exact release date and integration details are unknown.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Memory system for voice agents with a left brain for facts and a right brain for preferences and emotions, retrieving only relevant memories from a graph. It showed better memory accuracy, fewer tokens and sub-second latency than competing methods; code released.
Closest neighbours by meaning, not just by category.
Model
Research model for real-time, talking video agents with a single streaming Transformer; 640×368 output at ~200 ms latency.
Model · Thinking Machines
Thinking Machines' preview real-time model that processes audio, video and text continuously while responding.
App · OpenAI
OpenAI's ChatGPT memory system that synthesizes context from past chats in the background to keep memory current.
App · ElevenLabs
ElevenLabs platform for building, deploying and monitoring real-time voice and chat AI agents.
API · OpenAI
OpenAI API for realtime voice assistants that keep talking while background agents work.
API · ElevenLabs
AI audio platform and API for text-to-speech, speech-to-text, music, sound effects, voice cloning and voice agents.
